Upload final LoRA adapter artifacts

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,207 @@
+---
+base_model: google/gemma-4-e4b-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/gemma-4-e4b-it
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

adapter_config.json

@@ -0,0 +1,91 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-4-e4b-it",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": "language_model.layers",
+  "layers_to_transform": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10,
+    11,
+    12,
+    13,
+    14,
+    15,
+    16,
+    17,
+    18,
+    19,
+    20,
+    21,
+    22,
+    23,
+    24,
+    25,
+    26,
+    27,
+    28,
+    29,
+    30,
+    31,
+    32,
+    33,
+    34,
+    35,
+    36,
+    37,
+    38,
+    39,
+    40,
+    41
+  ],
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d065fae51a8cb3acae2dd90b6674d59983f73352c4209f99f68515850d10877f
+size 69839888

chat_template.jinja

@@ -0,0 +1,351 @@
+{%- macro format_parameters(properties, required, filter_keys=false) -%}
+    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in properties | dictsort -%}
+        {%- set add_comma = false -%}
+        {%- if not filter_keys or key not in standard_keys -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {{ key }}:{
+            {%- if value['description'] -%}
+                description:<|"|>{{ value['description'] }}<|"|>
+                {%- set add_comma = true -%}
+            {%- endif -%}
+            {%- if value['type'] | upper == 'STRING' -%}
+                {%- if value['enum'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    enum:{{ format_argument(value['enum']) }}
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'ARRAY' -%}
+                {%- if value['items'] is mapping and value['items'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    items:{
+                    {%- set ns_items = namespace(found_first=false) -%}
+                    {%- for item_key, item_value in value['items'] | dictsort -%}
+                        {%- if item_value is not none -%}
+                            {%- if ns_items.found_first %},{% endif -%}
+                            {%- set ns_items.found_first = true -%}
+                            {%- if item_key == 'properties' -%}
+                                properties:{
+                                {%- if item_value is mapping -%}
+                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
+                                {%- endif -%}
+                                }
+                            {%- elif item_key == 'required' -%}
+                                required:[
+                                {%- for req_item in item_value -%}
+                                    <|"|>{{- req_item -}}<|"|>
+                                    {%- if not loop.last %},{% endif -%}
+                                {%- endfor -%}
+                                ]
+                            {%- elif item_key == 'type' -%}
+                                {%- if item_value is string -%}
+                                    type:{{ format_argument(item_value | upper) }}
+                                {%- else -%}
+                                    type:{{ format_argument(item_value | map('upper') | list) }}
+                                {%- endif -%}
+                            {%- else -%}
+                                {{ item_key }}:{{ format_argument(item_value) }}
+                            {%- endif -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                    }
+                {%- endif -%}
+            {%- endif -%}
+            {%- if value['nullable'] %}
+                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                nullable:true
+            {%- endif -%}
+            {%- if value['type'] | upper == 'OBJECT' -%}
+                {%- if value['properties'] is defined and value['properties'] is mapping -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    properties:{
+                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
+                    }
+                {%- elif value is mapping -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    properties:{
+                    {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}
+                    }
+                {%- endif -%}
+                {%- if value['required'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <|"|>{{- item -}}<|"|>
+                        {%- if not loop.last %},{% endif -%}
+                    {%- endfor -%}
+                    ]
+                {%- endif -%}
+            {%- endif -%}
+            {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+            type:<|"|>{{ value['type'] | upper }}<|"|>}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro -%}
+{%- macro format_function_declaration(tool_data) -%}
+    declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
+    {%- set params = tool_data['function']['parameters'] -%}
+    {%- if params -%}
+        ,parameters:{
+        {%- if params['properties'] -%}
+            properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
+        {%- endif -%}
+        {%- if params['required'] -%}
+            required:[
+            {%- for item in params['required'] -%}
+                <|"|>{{- item -}}<|"|>
+                {{- ',' if not loop.last -}}
+            {%- endfor -%}
+            ],
+        {%- endif -%}
+        {%- if params['type'] -%}
+            type:<|"|>{{- params['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    {%- if 'response' in tool_data['function'] -%}
+        {%- set response_declaration = tool_data['function']['response'] -%}
+        ,response:{
+        {%- if response_declaration['description'] -%}
+            description:<|"|>{{- response_declaration['description'] -}}<|"|>,
+        {%- endif -%}
+        {%- if response_declaration['type'] | upper == 'OBJECT' -%}
+            type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    }
+{%- endmacro -%}
+{%- macro format_argument(argument, escape_keys=True) -%}
+    {%- if argument is string -%}
+        {{- '<|"|>' + argument + '<|"|>' -}}
+    {%- elif argument is boolean -%}
+        {{- 'true' if argument else 'false' -}}
+    {%- elif argument is mapping -%}
+        {{- '{' -}}
+        {%- set ns = namespace(found_first=false) -%}
+        {%- for key, value in argument | dictsort -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {%- if escape_keys -%}
+                {{- '<|"|>' + key + '<|"|>' -}}
+            {%- else -%}
+                {{- key -}}
+            {%- endif -%}
+            :{{- format_argument(value, escape_keys=escape_keys) -}}
+        {%- endfor -%}
+        {{- '}' -}}
+    {%- elif argument is sequence -%}
+        {{- '[' -}}
+        {%- for item in argument -%}
+            {{- format_argument(item, escape_keys=escape_keys) -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- ']' -}}
+    {%- else -%}
+        {{- argument -}}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro strip_thinking(text) -%}
+    {%- set ns = namespace(result='') -%}
+    {%- for part in text.split('<channel|>') -%}
+        {%- if '<|channel>' in part -%}
+            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
+        {%- else -%}
+            {%- set ns.result = ns.result + part -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- ns.result | trim -}}
+{%- endmacro -%}
+
+{%- macro format_tool_response_block(tool_name, response) -%}
+    {{- '<|tool_response>' -}}
+    {%- if response is mapping -%}
+        {{- 'response:' + tool_name + '{' -}}
+        {%- for key, value in response | dictsort -%}
+            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- '}' -}}
+    {%- else -%}
+        {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
+    {%- endif -%}
+    {{- '<tool_response|>' -}}
+{%- endmacro -%}
+
+{%- set ns = namespace(prev_message_type=None) -%}
+{%- set loop_messages = messages -%}
+{{- bos_token -}}
+{#- Handle System/Tool Definitions Block -#}
+{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}
+    {{- '<|turn>system\n' -}}
+    {#- Inject Thinking token at the very top of the FIRST system turn -#}
+    {%- if enable_thinking is defined and enable_thinking -%}
+        {{- '<|think|>\n' -}}
+        {%- set ns.prev_message_type = 'think' -%}
+    {%- endif -%}
+    {%- if messages[0]['role'] in ['system', 'developer'] -%}
+        {%- if messages[0]['content'] is string -%}
+            {{- messages[0]['content'] | trim -}}
+        {%- elif messages[0]['content'] is sequence -%}
+            {%- for item in messages[0]['content'] -%}
+                {{- item['text'] | trim + ' '-}}
+            {%- endfor -%}
+        {%- endif -%}
+        {%- set loop_messages = messages[1:] -%}
+    {%- endif -%}
+    {%- if tools -%}
+        {%- for tool in tools %}
+            {{- '<|tool>' -}}
+            {{- format_function_declaration(tool) | trim -}}
+            {{- '<tool|>' -}}
+        {%- endfor %}
+        {%- set ns.prev_message_type = 'tool' -%}
+    {%- endif -%}
+    {{- '<turn|>\n' -}}
+{%- endif %}
+
+{#- Pre-scan: find last user message index for reasoning guard -#}
+{%- set ns_turn = namespace(last_user_idx=-1) -%}
+{%- for i in range(loop_messages | length) -%}
+    {%- if loop_messages[i]['role'] == 'user' -%}
+        {%- set ns_turn.last_user_idx = i -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{#- Loop through messages -#}
+{%- for message in loop_messages -%}
+    {%- if message['role'] != 'tool' -%}
+    {%- set ns.prev_message_type = None -%}
+    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
+    {#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}
+    {%- set prev_nt = namespace(role=None, found=false) -%}
+    {%- if loop.index0 > 0 -%}
+        {%- for j in range(loop.index0 - 1, -1, -1) -%}
+            {%- if not prev_nt.found -%}
+                {%- if loop_messages[j]['role'] != 'tool' -%}
+                    {%- set prev_nt.role = loop_messages[j]['role'] -%}
+                    {%- set prev_nt.found = true -%}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- endif -%}
+    {%- set continue_same_model_turn = (role == 'model' and prev_nt.role == 'assistant') -%}
+    {%- if not continue_same_model_turn -%}
+        {{- '<|turn>' + role + '\n' }}
+    {%- endif -%}
+
+    {#- Render reasoning/reasoning_content as thinking channel -#}
+    {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
+    {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}
+        {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
+    {%- endif -%}
+
+            {%- if message['tool_calls'] -%}
+                {%- for tool_call in message['tool_calls'] -%}
+                    {%- set function = tool_call['function'] -%}
+                    {{- '<|tool_call>call:' + function['name'] + '{' -}}
+                    {%- if function['arguments'] is mapping -%}
+                        {%- set ns_args = namespace(found_first=false) -%}
+                        {%- for key, value in function['arguments'] | dictsort -%}
+                            {%- if ns_args.found_first %},{% endif -%}
+                            {%- set ns_args.found_first = true -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                        {%- endfor -%}
+                    {%- elif function['arguments'] is string -%}
+                        {{- function['arguments'] -}}
+                    {%- endif -%}
+                    {{- '}<tool_call|>' -}}
+                {%- endfor -%}
+                {%- set ns.prev_message_type = 'tool_call' -%}
+            {%- endif -%}
+
+            {%- set ns_tr_out = namespace(flag=false) -%}
+            {%- if message.get('tool_responses') -%}
+                {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
+                {%- for tool_response in message['tool_responses'] -%}
+                    {{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}
+                    {%- set ns_tr_out.flag = true -%}
+                    {%- set ns.prev_message_type = 'tool_response' -%}
+                {%- endfor -%}
+            {%- elif message.get('tool_calls') -%}
+                {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
+                {%- set ns_tool_scan = namespace(stopped=false) -%}
+                {%- for k in range(loop.index0 + 1, loop_messages | length) -%}
+                    {%- if ns_tool_scan.stopped -%}
+                    {%- elif loop_messages[k]['role'] != 'tool' -%}
+                        {%- set ns_tool_scan.stopped = true -%}
+                    {%- else -%}
+                        {%- set follow = loop_messages[k] -%}
+                        {#- Resolve tool_call_id to function name -#}
+                        {%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}
+                        {%- for tc in message['tool_calls'] -%}
+                            {%- if tc.get('id') == follow.get('tool_call_id') -%}
+                                {%- set ns_tname.name = tc['function']['name'] -%}
+                            {%- endif -%}
+                        {%- endfor -%}
+                        {#- Handle content as string or content-parts array -#}
+                        {%- set tool_body = follow.get('content') -%}
+                        {%- if tool_body is string -%}
+                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
+                        {%- elif tool_body is sequence and tool_body is not string -%}
+                            {%- set ns_txt = namespace(s='') -%}
+                            {%- for part in tool_body -%}
+                                {%- if part.get('type') == 'text' -%}
+                                    {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
+                                {%- endif -%}
+                            {%- endfor -%}
+                            {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
+                        {%- else -%}
+                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
+                        {%- endif -%}
+                        {%- set ns_tr_out.flag = true -%}
+                        {%- set ns.prev_message_type = 'tool_response' -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+
+            {%- set captured_content -%}
+            {%- if message['content'] is string -%}
+                {%- if role == 'model' -%}
+                    {{- strip_thinking(message['content']) -}}
+                {%- else -%}
+                    {{- message['content'] | trim -}}
+                {%- endif -%}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item['type'] == 'text' -%}
+                        {%- if role == 'model' -%}
+                            {{- strip_thinking(item['text']) -}}
+                        {%- else -%}
+                            {{- item['text'] | trim -}}
+                        {%- endif -%}
+                    {%- elif item['type'] == 'image' -%}
+                        {{- '<|image|>' -}}
+                        {%- set ns.prev_message_type = 'image' -%}
+                    {%- elif item['type'] == 'audio' -%}
+                        {{- '<|audio|>' -}}
+                        {%- set ns.prev_message_type = 'audio' -%}
+                    {%- elif item['type'] == 'video' -%}
+                        {{- '<|video|>' -}}
+                        {%- set ns.prev_message_type = 'video' -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+            {%- endset -%}
+
+            {{- captured_content -}}
+            {%- set has_content = captured_content | trim | length > 0 -%}
+
+        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
+            {{- '<|tool_response>' -}}
+        {%- elif not (ns_tr_out.flag and not has_content) -%}
+            {{- '<turn|>\n' -}}
+        {%- endif -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
+        {{- '<|turn>model\n' -}}
+    {%- endif -%}
+{%- endif -%}

processor_config.json

@@ -0,0 +1,75 @@
+{
+  "audio_ms_per_token": 40,
+  "audio_seq_length": 750,
+  "feature_extractor": {
+    "dither": 0.0,
+    "feature_extractor_type": "Gemma4AudioFeatureExtractor",
+    "feature_size": 128,
+    "fft_length": 512,
+    "fft_overdrive": false,
+    "frame_length": 320,
+    "hop_length": 160,
+    "input_scale_factor": 1.0,
+    "max_frequency": 8000.0,
+    "mel_floor": 0.001,
+    "min_frequency": 0.0,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "per_bin_mean": null,
+    "per_bin_stddev": null,
+    "preemphasis": 0.0,
+    "preemphasis_htk_flavor": true,
+    "return_attention_mask": true,
+    "sampling_rate": 16000
+  },
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": false,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_processor_type": "Gemma4ImageProcessor",
+    "image_seq_length": 280,
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 280,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098
+  },
+  "image_seq_length": 280,
+  "processor_class": "Gemma4Processor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 70,
+    "num_frames": 32,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "video_processor_type": "Gemma4VideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
+size 32169626

tokenizer_config.json

@@ -0,0 +1,95 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma4Processor",
+  "response_schema": {
+    "properties": {
+      "content": {
+        "type": "string"
+      },
+      "role": {
+        "const": "assistant"
+      },
+      "thinking": {
+        "type": "string"
+      },
+      "tool_calls": {
+        "items": {
+          "properties": {
+            "function": {
+              "properties": {
+                "arguments": {
+                  "additionalProperties": {},
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call"
+                },
+                "name": {
+                  "type": "string"
+                }
+              },
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
+            },
+            "type": {
+              "const": "function"
+            }
+          },
+          "type": "object"
+        },
+        "type": "array",
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
+      }
+    },
+    "type": "object",
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
+  },
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,862 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1170,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.025682182985553772,
+      "grad_norm": 41.89281463623047,
+      "learning_rate": 5e-05,
+      "loss": 41.062384033203124,
+      "step": 10
+    },
+    {
+      "epoch": 0.051364365971107544,
+      "grad_norm": 19.25795555114746,
+      "learning_rate": 0.00010555555555555557,
+      "loss": 23.114556884765626,
+      "step": 20
+    },
+    {
+      "epoch": 0.07704654895666131,
+      "grad_norm": 15.17092514038086,
+      "learning_rate": 0.0001611111111111111,
+      "loss": 19.892947387695312,
+      "step": 30
+    },
+    {
+      "epoch": 0.10272873194221509,
+      "grad_norm": 12.6154146194458,
+      "learning_rate": 0.0001999965463076377,
+      "loss": 18.954251098632813,
+      "step": 40
+    },
+    {
+      "epoch": 0.12841091492776885,
+      "grad_norm": 13.695039749145508,
+      "learning_rate": 0.00019993515396856082,
+      "loss": 18.60211944580078,
+      "step": 50
+    },
+    {
+      "epoch": 0.15409309791332262,
+      "grad_norm": 13.03475570678711,
+      "learning_rate": 0.00019979706714271113,
+      "loss": 17.00911102294922,
+      "step": 60
+    },
+    {
+      "epoch": 0.1797752808988764,
+      "grad_norm": 12.657264709472656,
+      "learning_rate": 0.0001995823918037908,
+      "loss": 16.737196350097655,
+      "step": 70
+    },
+    {
+      "epoch": 0.20545746388443017,
+      "grad_norm": 9.450530052185059,
+      "learning_rate": 0.00019929129270278366,
+      "loss": 17.192404174804686,
+      "step": 80
+    },
+    {
+      "epoch": 0.23113964686998395,
+      "grad_norm": 11.038394927978516,
+      "learning_rate": 0.0001989239932415185,
+      "loss": 17.626002502441406,
+      "step": 90
+    },
+    {
+      "epoch": 0.2568218298555377,
+      "grad_norm": 10.112431526184082,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 17.375982666015624,
+      "step": 100
+    },
+    {
+      "epoch": 0.2825040128410915,
+      "grad_norm": 10.951290130615234,
+      "learning_rate": 0.0001979619790261853,
+      "loss": 16.52630157470703,
+      "step": 110
+    },
+    {
+      "epoch": 0.30818619582664525,
+      "grad_norm": 13.097779273986816,
+      "learning_rate": 0.00019736800256273457,
+      "loss": 18.660000610351563,
+      "step": 120
+    },
+    {
+      "epoch": 0.33386837881219905,
+      "grad_norm": 10.489601135253906,
+      "learning_rate": 0.00019669930175366472,
+      "loss": 18.038082885742188,
+      "step": 130
+    },
+    {
+      "epoch": 0.3595505617977528,
+      "grad_norm": 12.037221908569336,
+      "learning_rate": 0.0001959563897884124,
+      "loss": 16.976956176757813,
+      "step": 140
+    },
+    {
+      "epoch": 0.3852327447833066,
+      "grad_norm": 13.149781227111816,
+      "learning_rate": 0.00019513983680921108,
+      "loss": 17.55983123779297,
+      "step": 150
+    },
+    {
+      "epoch": 0.41091492776886035,
+      "grad_norm": 12.796188354492188,
+      "learning_rate": 0.00019425026947353992,
+      "loss": 17.86356201171875,
+      "step": 160
+    },
+    {
+      "epoch": 0.43659711075441415,
+      "grad_norm": 14.400433540344238,
+      "learning_rate": 0.0001932883704732001,
+      "loss": 17.5066162109375,
+      "step": 170
+    },
+    {
+      "epoch": 0.4622792937399679,
+      "grad_norm": 16.03416633605957,
+      "learning_rate": 0.00019225487801038788,
+      "loss": 18.057034301757813,
+      "step": 180
+    },
+    {
+      "epoch": 0.48796147672552165,
+      "grad_norm": 11.53113842010498,
+      "learning_rate": 0.00019115058523116733,
+      "loss": 16.775308227539064,
+      "step": 190
+    },
+    {
+      "epoch": 0.5136436597110754,
+      "grad_norm": 12.079059600830078,
+      "learning_rate": 0.00018997633961677582,
+      "loss": 17.352998352050783,
+      "step": 200
+    },
+    {
+      "epoch": 0.5393258426966292,
+      "grad_norm": 11.70594310760498,
+      "learning_rate": 0.00018873304233323122,
+      "loss": 18.17870635986328,
+      "step": 210
+    },
+    {
+      "epoch": 0.565008025682183,
+      "grad_norm": 13.156736373901367,
+      "learning_rate": 0.00018742164753973855,
+      "loss": 16.766079711914063,
+      "step": 220
+    },
+    {
+      "epoch": 0.5906902086677368,
+      "grad_norm": 11.801448822021484,
+      "learning_rate": 0.0001860431616564278,
+      "loss": 17.98457489013672,
+      "step": 230
+    },
+    {
+      "epoch": 0.6163723916532905,
+      "grad_norm": 11.434338569641113,
+      "learning_rate": 0.0001845986425919841,
+      "loss": 17.011558532714844,
+      "step": 240
+    },
+    {
+      "epoch": 0.6420545746388443,
+      "grad_norm": 11.592355728149414,
+      "learning_rate": 0.00018308919893176396,
+      "loss": 18.073362731933592,
+      "step": 250
+    },
+    {
+      "epoch": 0.6677367576243981,
+      "grad_norm": 12.140549659729004,
+      "learning_rate": 0.00018151598908701947,
+      "loss": 17.267474365234374,
+      "step": 260
+    },
+    {
+      "epoch": 0.6934189406099518,
+      "grad_norm": 12.207261085510254,
+      "learning_rate": 0.00017988022040588416,
+      "loss": 17.970367431640625,
+      "step": 270
+    },
+    {
+      "epoch": 0.7191011235955056,
+      "grad_norm": 12.024649620056152,
+      "learning_rate": 0.000178183148246803,
+      "loss": 18.595138549804688,
+      "step": 280
+    },
+    {
+      "epoch": 0.7447833065810594,
+      "grad_norm": 10.953705787658691,
+      "learning_rate": 0.0001764260750151167,
+      "loss": 17.661044311523437,
+      "step": 290
+    },
+    {
+      "epoch": 0.7704654895666132,
+      "grad_norm": 12.161933898925781,
+      "learning_rate": 0.0001746103491635407,
+      "loss": 17.323040771484376,
+      "step": 300
+    },
+    {
+      "epoch": 0.7961476725521669,
+      "grad_norm": 14.1478271484375,
+      "learning_rate": 0.00017273736415730488,
+      "loss": 17.589439392089844,
+      "step": 310
+    },
+    {
+      "epoch": 0.8218298555377207,
+      "grad_norm": 11.344724655151367,
+      "learning_rate": 0.0001708085574047494,
+      "loss": 18.087261962890626,
+      "step": 320
+    },
+    {
+      "epoch": 0.8475120385232745,
+      "grad_norm": 11.49538803100586,
+      "learning_rate": 0.00016882540915419623,
+      "loss": 16.709014892578125,
+      "step": 330
+    },
+    {
+      "epoch": 0.8731942215088283,
+      "grad_norm": 11.975954055786133,
+      "learning_rate": 0.00016678944135794374,
+      "loss": 18.784584045410156,
+      "step": 340
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 10.979130744934082,
+      "learning_rate": 0.00016470221650425582,
+      "loss": 17.035598754882812,
+      "step": 350
+    },
+    {
+      "epoch": 0.9245585874799358,
+      "grad_norm": 10.86307144165039,
+      "learning_rate": 0.00016256533641824177,
+      "loss": 17.912120056152343,
+      "step": 360
+    },
+    {
+      "epoch": 0.9502407704654896,
+      "grad_norm": 11.18655776977539,
+      "learning_rate": 0.00016038044103254775,
+      "loss": 16.4998046875,
+      "step": 370
+    },
+    {
+      "epoch": 0.9759229534510433,
+      "grad_norm": 11.321154594421387,
+      "learning_rate": 0.00015814920712880267,
+      "loss": 17.580471801757813,
+      "step": 380
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.271613597869873,
+      "learning_rate": 0.0001558733470507847,
+      "loss": 15.328689575195312,
+      "step": 390
+    },
+    {
+      "epoch": 1.0256821829855538,
+      "grad_norm": 13.181764602661133,
+      "learning_rate": 0.00015355460739029586,
+      "loss": 15.265965270996094,
+      "step": 400
+    },
+    {
+      "epoch": 1.0513643659711076,
+      "grad_norm": 11.904574394226074,
+      "learning_rate": 0.00015119476764675305,
+      "loss": 14.833596801757812,
+      "step": 410
+    },
+    {
+      "epoch": 1.0770465489566614,
+      "grad_norm": 12.352519989013672,
+      "learning_rate": 0.0001487956388615247,
+      "loss": 13.833314514160156,
+      "step": 420
+    },
+    {
+      "epoch": 1.102728731942215,
+      "grad_norm": 15.478001594543457,
+      "learning_rate": 0.00014635906222806058,
+      "loss": 15.767561340332032,
+      "step": 430
+    },
+    {
+      "epoch": 1.1284109149277688,
+      "grad_norm": 15.335821151733398,
+      "learning_rate": 0.00014388690767888154,
+      "loss": 14.462684631347656,
+      "step": 440
+    },
+    {
+      "epoch": 1.1540930979133226,
+      "grad_norm": 16.043373107910156,
+      "learning_rate": 0.00014138107245051392,
+      "loss": 15.908651733398438,
+      "step": 450
+    },
+    {
+      "epoch": 1.1797752808988764,
+      "grad_norm": 12.852351188659668,
+      "learning_rate": 0.00013884347962746948,
+      "loss": 15.758128356933593,
+      "step": 460
+    },
+    {
+      "epoch": 1.2054574638844302,
+      "grad_norm": 15.320487022399902,
+      "learning_rate": 0.00013627607666638858,
+      "loss": 15.051063537597656,
+      "step": 470
+    },
+    {
+      "epoch": 1.231139646869984,
+      "grad_norm": 16.30264663696289,
+      "learning_rate": 0.00013368083390147913,
+      "loss": 14.599794006347656,
+      "step": 480
+    },
+    {
+      "epoch": 1.2568218298555376,
+      "grad_norm": 13.734286308288574,
+      "learning_rate": 0.00013105974303239838,
+      "loss": 14.052903747558593,
+      "step": 490
+    },
+    {
+      "epoch": 1.2825040128410916,
+      "grad_norm": 15.704442024230957,
+      "learning_rate": 0.0001284148155957379,
+      "loss": 13.530386352539063,
+      "step": 500
+    },
+    {
+      "epoch": 1.3081861958266452,
+      "grad_norm": 14.808961868286133,
+      "learning_rate": 0.00012574808142128477,
+      "loss": 14.240873718261719,
+      "step": 510
+    },
+    {
+      "epoch": 1.333868378812199,
+      "grad_norm": 13.389018058776855,
+      "learning_rate": 0.00012306158707424403,
+      "loss": 14.467668151855468,
+      "step": 520
+    },
+    {
+      "epoch": 1.3595505617977528,
+      "grad_norm": 16.077634811401367,
+      "learning_rate": 0.00012035739428461739,
+      "loss": 13.67303466796875,
+      "step": 530
+    },
+    {
+      "epoch": 1.3852327447833066,
+      "grad_norm": 14.300647735595703,
+      "learning_rate": 0.00011763757836494403,
+      "loss": 15.072747802734375,
+      "step": 540
+    },
+    {
+      "epoch": 1.4109149277688604,
+      "grad_norm": 12.59499454498291,
+      "learning_rate": 0.00011490422661761744,
+      "loss": 14.030448913574219,
+      "step": 550
+    },
+    {
+      "epoch": 1.4365971107544142,
+      "grad_norm": 17.819976806640625,
+      "learning_rate": 0.00011215943673300093,
+      "loss": 13.556326293945313,
+      "step": 560
+    },
+    {
+      "epoch": 1.462279293739968,
+      "grad_norm": 15.307595252990723,
+      "learning_rate": 0.00010940531517957073,
+      "loss": 15.464706420898438,
+      "step": 570
+    },
+    {
+      "epoch": 1.4879614767255216,
+      "grad_norm": 14.918625831604004,
+      "learning_rate": 0.00010664397558732244,
+      "loss": 14.040945434570313,
+      "step": 580
+    },
+    {
+      "epoch": 1.5136436597110754,
+      "grad_norm": 13.040802955627441,
+      "learning_rate": 0.0001038775371256817,
+      "loss": 14.671842956542969,
+      "step": 590
+    },
+    {
+      "epoch": 1.5393258426966292,
+      "grad_norm": 14.143183708190918,
+      "learning_rate": 0.00010110812287716327,
+      "loss": 14.198591613769532,
+      "step": 600
+    },
+    {
+      "epoch": 1.565008025682183,
+      "grad_norm": 16.373567581176758,
+      "learning_rate": 9.833785820802739e-05,
+      "loss": 14.670704650878907,
+      "step": 610
+    },
+    {
+      "epoch": 1.5906902086677368,
+      "grad_norm": 17.14202117919922,
+      "learning_rate": 9.556886913718317e-05,
+      "loss": 14.713813781738281,
+      "step": 620
+    },
+    {
+      "epoch": 1.6163723916532904,
+      "grad_norm": 13.428468704223633,
+      "learning_rate": 9.280328070459135e-05,
+      "loss": 14.256681823730469,
+      "step": 630
+    },
+    {
+      "epoch": 1.6420545746388444,
+      "grad_norm": 14.759570121765137,
+      "learning_rate": 9.004321534041835e-05,
+      "loss": 14.875436401367187,
+      "step": 640
+    },
+    {
+      "epoch": 1.667736757624398,
+      "grad_norm": 14.605072021484375,
+      "learning_rate": 8.729079123619286e-05,
+      "loss": 14.151382446289062,
+      "step": 650
+    },
+    {
+      "epoch": 1.6934189406099518,
+      "grad_norm": 15.300275802612305,
+      "learning_rate": 8.454812071921596e-05,
+      "loss": 14.209205627441406,
+      "step": 660
+    },
+    {
+      "epoch": 1.7191011235955056,
+      "grad_norm": 15.565445899963379,
+      "learning_rate": 8.181730863147093e-05,
+      "loss": 15.246949768066406,
+      "step": 670
+    },
+    {
+      "epoch": 1.7447833065810594,
+      "grad_norm": 13.463878631591797,
+      "learning_rate": 7.910045071427829e-05,
+      "loss": 14.081675720214843,
+      "step": 680
+    },
+    {
+      "epoch": 1.7704654895666132,
+      "grad_norm": 15.799697875976562,
+      "learning_rate": 7.63996319999347e-05,
+      "loss": 14.659947204589844,
+      "step": 690
+    },
+    {
+      "epoch": 1.7961476725521668,
+      "grad_norm": 15.421786308288574,
+      "learning_rate": 7.371692521157048e-05,
+      "loss": 13.642781066894532,
+      "step": 700
+    },
+    {
+      "epoch": 1.8218298555377208,
+      "grad_norm": 16.400951385498047,
+      "learning_rate": 7.10543891724537e-05,
+      "loss": 14.9028076171875,
+      "step": 710
+    },
+    {
+      "epoch": 1.8475120385232744,
+      "grad_norm": 16.549213409423828,
+      "learning_rate": 6.841406722596191e-05,
+      "loss": 14.747923278808594,
+      "step": 720
+    },
+    {
+      "epoch": 1.8731942215088284,
+      "grad_norm": 14.868678092956543,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 14.379522705078125,
+      "step": 730
+    },
+    {
+      "epoch": 1.898876404494382,
+      "grad_norm": 17.223217010498047,
+      "learning_rate": 6.320815218910101e-05,
+      "loss": 14.513031005859375,
+      "step": 740
+    },
+    {
+      "epoch": 1.9245585874799358,
+      "grad_norm": 15.178607940673828,
+      "learning_rate": 6.064655433930624e-05,
+      "loss": 14.75238494873047,
+      "step": 750
+    },
+    {
+      "epoch": 1.9502407704654896,
+      "grad_norm": 14.607568740844727,
+      "learning_rate": 5.8115157997167536e-05,
+      "loss": 14.215359497070313,
+      "step": 760
+    },
+    {
+      "epoch": 1.9759229534510432,
+      "grad_norm": 15.849374771118164,
+      "learning_rate": 5.561590586388221e-05,
+      "loss": 13.844842529296875,
+      "step": 770
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.945368766784668,
+      "learning_rate": 5.315071597181504e-05,
+      "loss": 13.500308227539062,
+      "step": 780
+    },
+    {
+      "epoch": 2.0256821829855536,
+      "grad_norm": 14.872233390808105,
+      "learning_rate": 5.072148021251821e-05,
+      "loss": 10.96926498413086,
+      "step": 790
+    },
+    {
+      "epoch": 2.0513643659711076,
+      "grad_norm": 16.96340560913086,
+      "learning_rate": 4.833006288481371e-05,
+      "loss": 10.601210021972657,
+      "step": 800
+    },
+    {
+      "epoch": 2.077046548956661,
+      "grad_norm": 17.987470626831055,
+      "learning_rate": 4.597829926405075e-05,
+      "loss": 11.348848724365235,
+      "step": 810
+    },
+    {
+      "epoch": 2.102728731942215,
+      "grad_norm": 18.53151512145996,
+      "learning_rate": 4.3667994193637796e-05,
+      "loss": 10.507981109619141,
+      "step": 820
+    },
+    {
+      "epoch": 2.128410914927769,
+      "grad_norm": 23.948802947998047,
+      "learning_rate": 4.140092069992867e-05,
+      "loss": 11.215933227539063,
+      "step": 830
+    },
+    {
+      "epoch": 2.154093097913323,
+      "grad_norm": 21.3605899810791,
+      "learning_rate": 3.91788186315269e-05,
+      "loss": 10.393006896972656,
+      "step": 840
+    },
+    {
+      "epoch": 2.1797752808988764,
+      "grad_norm": 26.548303604125977,
+      "learning_rate": 3.7003393324051874e-05,
+      "loss": 10.384098052978516,
+      "step": 850
+    },
+    {
+      "epoch": 2.20545746388443,
+      "grad_norm": 23.979907989501953,
+      "learning_rate": 3.487631429139183e-05,
+      "loss": 10.094139862060548,
+      "step": 860
+    },
+    {
+      "epoch": 2.231139646869984,
+      "grad_norm": 18.00309944152832,
+      "learning_rate": 3.279921394444776e-05,
+      "loss": 10.624467468261718,
+      "step": 870
+    },
+    {
+      "epoch": 2.2568218298555376,
+      "grad_norm": 24.657569885253906,
+      "learning_rate": 3.077368633835205e-05,
+      "loss": 10.711078643798828,
+      "step": 880
+    },
+    {
+      "epoch": 2.2825040128410916,
+      "grad_norm": 22.551204681396484,
+      "learning_rate": 2.8801285949122593e-05,
+      "loss": 10.329103088378906,
+      "step": 890
+    },
+    {
+      "epoch": 2.308186195826645,
+      "grad_norm": 26.180330276489258,
+      "learning_rate": 2.688352648069198e-05,
+      "loss": 9.944695281982423,
+      "step": 900
+    },
+    {
+      "epoch": 2.333868378812199,
+      "grad_norm": 34.10860061645508,
+      "learning_rate": 2.502187970322657e-05,
+      "loss": 10.465196990966797,
+      "step": 910
+    },
+    {
+      "epoch": 2.359550561797753,
+      "grad_norm": 25.76052474975586,
+      "learning_rate": 2.321777432362764e-05,
+      "loss": 10.892754364013673,
+      "step": 920
+    },
+    {
+      "epoch": 2.3852327447833064,
+      "grad_norm": 25.387516021728516,
+      "learning_rate": 2.1472594889080756e-05,
+      "loss": 10.628679656982422,
+      "step": 930
+    },
+    {
+      "epoch": 2.4109149277688604,
+      "grad_norm": 22.750202178955078,
+      "learning_rate": 1.9787680724495617e-05,
+      "loss": 10.46801986694336,
+      "step": 940
+    },
+    {
+      "epoch": 2.436597110754414,
+      "grad_norm": 29.39733123779297,
+      "learning_rate": 1.8164324904650965e-05,
+      "loss": 11.32564697265625,
+      "step": 950
+    },
+    {
+      "epoch": 2.462279293739968,
+      "grad_norm": 23.36044692993164,
+      "learning_rate": 1.660377326183412e-05,
+      "loss": 10.110736083984374,
+      "step": 960
+    },
+    {
+      "epoch": 2.4879614767255216,
+      "grad_norm": 22.447628021240234,
+      "learning_rate": 1.5107223429736272e-05,
+      "loss": 10.582487487792969,
+      "step": 970
+    },
+    {
+      "epoch": 2.513643659711075,
+      "grad_norm": 21.37103271484375,
+      "learning_rate": 1.3675823924337506e-05,
+      "loss": 9.974002838134766,
+      "step": 980
+    },
+    {
+      "epoch": 2.539325842696629,
+      "grad_norm": 23.942567825317383,
+      "learning_rate": 1.2310673262486705e-05,
+      "loss": 10.401480102539063,
+      "step": 990
+    },
+    {
+      "epoch": 2.5650080256821832,
+      "grad_norm": 23.232219696044922,
+      "learning_rate": 1.1012819118853147e-05,
+      "loss": 10.403594970703125,
+      "step": 1000
+    },
+    {
+      "epoch": 2.590690208667737,
+      "grad_norm": 26.392332077026367,
+      "learning_rate": 9.783257521896227e-06,
+      "loss": 11.170610046386718,
+      "step": 1010
+    },
+    {
+      "epoch": 2.6163723916532904,
+      "grad_norm": 22.941421508789062,
+      "learning_rate": 8.62293208947107e-06,
+      "loss": 9.754792785644531,
+      "step": 1020
+    },
+    {
+      "epoch": 2.6420545746388444,
+      "grad_norm": 31.97374153137207,
+      "learning_rate": 7.532733304655848e-06,
+      "loss": 10.895748138427734,
+      "step": 1030
+    },
+    {
+      "epoch": 2.667736757624398,
+      "grad_norm": 22.15962791442871,
+      "learning_rate": 6.5134978323574066e-06,
+      "loss": 10.086806488037109,
+      "step": 1040
+    },
+    {
+      "epoch": 2.693418940609952,
+      "grad_norm": 23.121976852416992,
+      "learning_rate": 5.566007877218882e-06,
+      "loss": 9.806757354736328,
+      "step": 1050
+    },
+    {
+      "epoch": 2.7191011235955056,
+      "grad_norm": 22.89173698425293,
+      "learning_rate": 4.6909905833226966e-06,
+      "loss": 9.998442077636719,
+      "step": 1060
+    },
+    {
+      "epoch": 2.744783306581059,
+      "grad_norm": 28.151565551757812,
+      "learning_rate": 3.8891174761491735e-06,
+      "loss": 10.232617950439453,
+      "step": 1070
+    },
+    {
+      "epoch": 2.770465489566613,
+      "grad_norm": 27.67608070373535,
+      "learning_rate": 3.161003947219421e-06,
+      "loss": 11.071966552734375,
+      "step": 1080
+    },
+    {
+      "epoch": 2.796147672552167,
+      "grad_norm": 26.361303329467773,
+      "learning_rate": 2.5072087818176382e-06,
+      "loss": 11.048786926269532,
+      "step": 1090
+    },
+    {
+      "epoch": 2.821829855537721,
+      "grad_norm": 24.121335983276367,
+      "learning_rate": 1.928233730155604e-06,
+      "loss": 10.665110015869141,
+      "step": 1100
+    },
+    {
+      "epoch": 2.8475120385232744,
+      "grad_norm": 26.22313117980957,
+      "learning_rate": 1.4245231223081301e-06,
+      "loss": 11.044110107421876,
+      "step": 1110
+    },
+    {
+      "epoch": 2.8731942215088284,
+      "grad_norm": 26.499591827392578,
+      "learning_rate": 9.964635272153633e-07,
+      "loss": 10.147935485839843,
+      "step": 1120
+    },
+    {
+      "epoch": 2.898876404494382,
+      "grad_norm": 23.90386390686035,
+      "learning_rate": 6.443834560132534e-07,
+      "loss": 10.296646881103516,
+      "step": 1130
+    },
+    {
+      "epoch": 2.924558587479936,
+      "grad_norm": 24.210269927978516,
+      "learning_rate": 3.685531099202111e-07,
+      "loss": 10.592522430419923,
+      "step": 1140
+    },
+    {
+      "epoch": 2.9502407704654896,
+      "grad_norm": 28.532909393310547,
+      "learning_rate": 1.6918417287318245e-07,
+      "loss": 9.853338623046875,
+      "step": 1150
+    },
+    {
+      "epoch": 2.975922953451043,
+      "grad_norm": 27.218006134033203,
+      "learning_rate": 4.642964907235481e-08,
+      "loss": 10.533452606201172,
+      "step": 1160
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 14.907074928283691,
+      "learning_rate": 3.837455592847761e-10,
+      "loss": 9.5769775390625,
+      "step": 1170
+    },
+    {
+      "epoch": 3.0,
+      "step": 1170,
+      "total_flos": 2.709259627140219e+17,
+      "train_loss": 14.446504472259782,
+      "train_runtime": 5026.5595,
+      "train_samples_per_second": 1.859,
+      "train_steps_per_second": 0.233
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1170,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.709259627140219e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2be588ff8c8b6fcd8303c648ab8d3bf2aa58bf5fcdc6821e6579f3a61a41feff
+size 6737